From owner-freebsd-hackers Thu Nov 16 11:09:30 1995 Return-Path: owner-hackers Received: (from root@localhost) by freefall.freebsd.org (8.6.12/8.6.6) id LAA06845 for hackers-outgoing; Thu, 16 Nov 1995 11:09:30 -0800 Received: from who.cdrom.com (who.cdrom.com [192.216.222.3]) by freefall.freebsd.org (8.6.12/8.6.6) with ESMTP id LAA06840 for ; Thu, 16 Nov 1995 11:09:29 -0800 Received: from phaeton.artisoft.com (phaeton.Artisoft.COM [198.17.250.211]) by who.cdrom.com (8.6.12/8.6.11) with ESMTP id LAA03498 for ; Thu, 16 Nov 1995 11:09:18 -0800 Received: (from terry@localhost) by phaeton.artisoft.com (8.6.11/8.6.9) id MAA03474; Thu, 16 Nov 1995 12:04:48 -0700 From: Terry Lambert Message-Id: <199511161904.MAA03474@phaeton.artisoft.com> Subject: Re: IDE drives using DMA? To: koshy@blr.novell.com Date: Thu, 16 Nov 1995 12:04:48 -0700 (MST) Cc: hackers@FreeBSD.ORG In-Reply-To: <30aacced0.2096@novidc.blr.novell.com> from "koshy@blr.novell.com" at Nov 16, 95 11:02:00 am X-Mailer: ELM [version 2.4 PL24] MIME-Version: 1.0 Content-Type: text/plain; charset=US-ASCII Content-Transfer-Encoding: 7bit Content-Length: 717 Sender: owner-hackers@FreeBSD.ORG Precedence: bulk > I chanced upon a book about ATA drives and noted there that IDE can > optionally support DMA transfers in addition to the regular programmed > IO. > > Does anyone have any experience with this? Are such configurations > common? Any catches or caveats that hinder DMA use with IDE drives? The most common IDE chip, the RZ1000, will silently corrupt data if you get *any* interrupt during a DMA transfer. This was discussed in great, gory detail on comp.sys.intel (Intel makes the RZ1000). This affects something like 1/3 to 1/2 of all IDE interfaces currently out there. Terry Lambert terry@lambert.org --- Any opinions in this posting are my own and not those of my present or previous employers.